{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T16:46:04Z","timestamp":1779122764435,"version":"3.51.4"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319544069","type":"print"},{"value":"9783319544076","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-54407-6_18","type":"book-chapter","created":{"date-parts":[[2017,3,14]],"date-time":"2017-03-14T02:04:07Z","timestamp":1489457047000},"page":"269-286","source":"Crossref","is-referenced-by-count":6,"title":["Video Captioning via Sentence Augmentation and Spatio-Temporal Attention"],"prefix":"10.1007","author":[{"given":"Tseng-Hung","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuo-Hao","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wan-Ting","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,3,15]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Deep compositional question answering with neural module networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.12"},{"key":"18_CR2","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. arXiv preprint arXiv:1412.7755 (2014)"},{"key":"18_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"18_CR4","unstructured":"Barbu, A., Bridge, E., Burchill, Z., Coroian, D., Dickinson, S., Fidler, S., Michaux, A., Mussman, S., Narayanaswamy, S., Salvi, D., Schmidt, L., Shangguan, J., Siskind, J.M., Waggoner, J., Wang, S., Wei, J., Yin, Y., Zhang, Z.: Video in sentences out. In: UAI (2012)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Chan, F.-H., Chen, Y.-T., Xiang, Y., Sun, M.: Anticipating accidents in dashcam videos. In: ACCV (2016)","DOI":"10.1007\/978-3-319-54190-7_9"},{"key":"18_CR6","unstructured":"Chen, D.L., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: NAACL-HLT, pp. 190\u2013200. Association for Computational Linguistics (2011)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Das, P., Xu, C., Doell, R., Corso, J.: A thousand frames in just a few words: lingual description of videos through latent topics and sparse object stitching. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.340"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"18_CR10","unstructured":"Abadi, M., et al.: TensorFlow: Large-scale machine learning on heterogeneous systems (2015). www.tensorflow.org"},{"key":"18_CR11","unstructured":"Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: ICML, vol. 14, pp. 1764\u20131772 (2014)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Guadarrama, S., Krishnamoorthy, N., Malkarnenkar, G., Venugopalan, S., Mooney, R., Darrell, T., Saenko, K.: Youtube2text: recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.337"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Venugopalan, S., Rohrbach, M., Mooney, R., Saenko, K., Darrell, T.: Deep compositional captioning: describing novel object categories without paired training data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.8"},{"key":"18_CR15","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Hu, R., Xu, H., Rohrbach, M., Feng, J., Saenko, K., Darrell, T.: Natural language object retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.493"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Kalal, Z., Mikolajczyk, K., Matas, J.: Forward-backward error: automatic detection of tracking failures. In: 2010 20th International Conference on Pattern recognition (ICPR), pp. 2756\u20132759. IEEE (2010)","DOI":"10.1109\/ICPR.2010.675"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"18_CR20","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv:1412.6980 (2014)"},{"key":"18_CR21","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)"},{"issue":"2","key":"18_CR22","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1023\/A:1020346032608","volume":"50","author":"A Kojima","year":"2002","unstructured":"Kojima, A., Tamura, T., Fukunaga, K.: Natural language description of human activities from video images based on concept hierarchy of actions. IJCV 50(2), 171\u2013184 (2002)","journal-title":"IJCV"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L.-J., Shamma, D.A., et al.: Visual genome: Connecting language and vision using crowdsourced dense image annotations. arXiv preprint arXiv:1602.07332 (2016)","DOI":"10.1007\/s11263-016-0981-7"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Krishnamoorthy, N., Malkarnenkar, G., Mooney, R.J., Saenko, K., Guadarrama, S.: Generating natural-language video descriptions using text-mined knowledge. In: AAAI (2013)","DOI":"10.1609\/aaai.v27i1.8679"},{"key":"18_CR25","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) NIPS (2012)"},{"issue":"11","key":"18_CR26","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"18_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). doi: 10.1007\/978-3-319-10602-1_48"},{"key":"18_CR28","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv:1301.3781 (2013)"},{"key":"18_CR29","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems, pp. 2204\u20132212 (2014)"},{"key":"18_CR30","unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Pan, P., Xu, Z., Yang, Y., Wu, F., Zhuang, Y.: Hierarchical recurrent neural encoder for video representation with application to captioning. arXiv:1511.03476 (2015)","DOI":"10.1109\/CVPR.2016.117"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Pan, Y., Mei, T., Yao, T., Li, H., Rui, Y.: Jointly modeling embedding and translation to bridge video and language. arXiv:1505.01861 (2015)","DOI":"10.1109\/CVPR.2016.497"},{"key":"18_CR33","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"18_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/978-3-319-24947-6_17","volume-title":"Pattern Recognition","author":"A Rohrbach","year":"2015","unstructured":"Rohrbach, A., Rohrbach, M., Schiele, B.: The long-short story of movie description. In: Gall, J., Gehler, P., Leibe, B. (eds.) GCPR 2015. LNCS, vol. 9358, pp. 209\u2013221. Springer, Cham (2015). doi: 10.1007\/978-3-319-24947-6_17"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Tandon, N., Schiele, B.: A dataset for movie description. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Qiu, W., Titov, I., Thater, S., Pinkal, M., Schiele, B.: Translating video content to natural language descriptions. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.61"},{"issue":"3","key":"18_CR37","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: Imagenet large scale visual recognition challenge. IJCV 115(3), 211\u2013252 (2015)","journal-title":"IJCV"},{"key":"18_CR38","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"18_CR39","unstructured":"Sukhbaatar, S., Weston, J., Fergus, R.: End-to-end memory networks. In: NIPS (2015)"},{"key":"18_CR40","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NIPS, pp. 3104\u20133112 (2014)"},{"key":"18_CR41","unstructured":"Thomason, J., Venugopalan, S., Guadarrama, S., Saenko, K., Mooney, R.: Integrating language and vision to generate natural language descriptions of videos in the wild. In: COLING (2014)"},{"key":"18_CR42","unstructured":"Torabi, A., Pal, C.J., Larochelle, H., Courville, A.C.: Using descriptive video services to create a large data source for video annotation research. arXiv:1503.01070 (2015)"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence - video to text. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R., Saenko, K.: Translating videos to natural language using deep recurrent neural networks. In: NAACL (2015)","DOI":"10.3115\/v1\/N15-1173"},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"18_CR47","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"18_CR48","doi-asserted-by":"crossref","unstructured":"Xu, H., Saenko, K.: Ask, attend and answer: Exploring question-guided spatial attention for visual question answering. arXiv preprint arXiv:1511.05234 (2015)","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"18_CR49","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"18_CR50","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R.S., Bengio, Y.: Show, attend and tell: Neural image caption generation with visual attention. arXiv preprint arXiv:1502.03044 2(3): 5 (2015)"},{"key":"18_CR51","doi-asserted-by":"crossref","unstructured":"Xu, R., Xiong, C., Chen, W., Corso, J.J.: Jointly modeling deep video and compositional text to bridge vision and language in a unified framework. In: AAAI, pp. 2346\u20132352 (2015)","DOI":"10.1609\/aaai.v29i1.9512"},{"key":"18_CR52","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. arXiv preprint arXiv:1511.02274 (2015)","DOI":"10.1109\/CVPR.2016.10"},{"key":"18_CR53","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., Ballas, N., Pal, C., Larochelle, H., Courville, A.: Describing videos by exploiting temporal structure. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"18_CR54","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"18_CR55","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, J., Huang, Z., Yang, Y., Xu, W.: Video paragraph captioning using hierarchical recurrent neural networks. arXiv:1510.07712 (2015)","DOI":"10.1109\/CVPR.2016.496"},{"key":"18_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1007\/978-3-319-46475-6_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K-H Zeng","year":"2016","unstructured":"Zeng, K.-H., Chen, T.-H., Niebles, J.C., Sun, M.: Title generation for user generated videos. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 609\u2013625. Springer, Cham (2016). doi: 10.1007\/978-3-319-46475-6_38"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2016 Workshops"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-54407-6_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T19:47:34Z","timestamp":1750103254000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-54407-6_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319544069","9783319544076"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-54407-6_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]}}}